CN116665102A - Intelligent control system of trash remover based on vision AI recognition algorithm - Google Patents
Intelligent control system of trash remover based on vision AI recognition algorithm Download PDFInfo
- Publication number
- CN116665102A CN116665102A CN202310632391.8A CN202310632391A CN116665102A CN 116665102 A CN116665102 A CN 116665102A CN 202310632391 A CN202310632391 A CN 202310632391A CN 116665102 A CN116665102 A CN 116665102A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- control system
- trash
- trash remover
- grab bucket
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 114
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 40
- 238000004140 cleaning Methods 0.000 claims abstract description 36
- 238000007667 floating Methods 0.000 claims abstract description 34
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 238000005259 measurement Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims abstract description 6
- 238000009825 accumulation Methods 0.000 claims abstract 2
- 238000004891 communication Methods 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 17
- 230000033001 locomotion Effects 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 2
- 210000001503 joint Anatomy 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 description 13
- 208000034699 Vitreous floaters Diseases 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000000034 method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000010865 sewage Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 101710200914 1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase 1 Proteins 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000124033 Salix Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005202 decontamination Methods 0.000 description 1
- 230000003588 decontaminative effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Electromagnetism (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Control Of Non-Electrical Variables (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses an intelligent control system of a trash remover based on a visual AI (advanced technology attachment) recognition algorithm, which comprises an intelligent decision platform and an intelligent driving control system, wherein the intelligent decision platform carries out trash removal inspection, shape and position recognition, accumulation measurement and calculation, trash removal decision and logic judgment exceeding an early warning threshold value through the visual AI algorithm, and automatically sends a trash removal planning command to the intelligent driving control system, and the intelligent driving control system receives a control command of the intelligent decision platform to control the trash remover to carry out trash removal operation. The intelligent recognition, automatic cleaning and centralized control remote semi-automatic cleaning operation of the floating matters at the water inlet of the trash rack are realized, so that the intelligent level of power station equipment is improved, the requirements of a remote centralized control center on supervision and cleaning of the floating trash at the water surface of the trash rack at the water inlet of the Liu Ping gate head are met, and meanwhile, the working intensity of working operation of people in main flood season is relieved.
Description
Technical Field
The invention relates to an intelligent control system of a trash remover, in particular to an intelligent control system of a trash remover based on a visual AI recognition algorithm.
Background
Artificial Intelligence (AI) is a theory, method, technique, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and extend human intelligence. The current domestic artificial intelligence market mainly comprises computer vision, voice, natural language processing, a basic algorithm platform and a chip. Computer vision is the most important part in the artificial intelligence market, is also the main technical application of artificial intelligence, and has the proportion of about 35 percent, and the industry chain is relatively mature. The reservoir of prior art is in the time of flood season dross more, need in time drag for the sediment clearance, and present willow floodgate trash remover can only be through local handle control, can not centralized control remote control, can not be emergent when the road is interrupted carry out long-range trash removal operation, influences the safe and stable operation of unit.
The cleaning operation in the prior art mainly takes manual inspection judgment and grid difference feedback as main, does not have intelligent recognition and automatic cleaning functions, a certain time interval exists in manual inspection, once grid difference alarm feedback is performed, the condition that the cleaning operation time allowance is insufficient is caused, the unit is liable to be subjected to load reduction or shutdown to avoid peaks, and the economic loss of power generation of the river basin step power station is caused. The horizontal travelling mechanism of the trash remover has the length of about 60 meters, and the manual repeated circulation mode of 'one grabbing and one releasing' is adopted for slag removing operation, so that the labor intensity is high.
Disclosure of Invention
The invention aims to provide an intelligent control system of a trash remover based on a visual AI recognition algorithm.
In order to achieve the above purpose, the invention is implemented according to the following technical scheme:
the intelligent decision platform carries out the logic judgment of the dirt cleaning inspection, the shape and position recognition, the product measurement and calculation, the dirt cleaning decision and the exceeding of the early warning threshold value through a visual AI algorithm, and automatically sends a dirt cleaning plan command to the intelligent drive control system, and the intelligent drive control system receives the control command of the intelligent decision platform to control the dirt cleaner to carry out the dirt cleaning operation.
The intelligent decision platform takes a perception intelligent technology as a core, and an optical non-contact sensing device is used for automatically receiving a large amount of water scene images for processing and performing intelligent analysis so as to obtain an information control machine or flow, and the internet, 5G or the Internet of things is fully utilized to build the intelligent analysis decision platform for early warning, processing and tracking of water surface pollution.
The intelligent driving control system is in communication connection with the orifice intelligent cleaning control system through an Ethernet, is in communication connection with the cleaning site centralized control system through the Ethernet, is in communication connection with the cleaning site centralized control system through Zigbee, and is in communication connection with the environment sensing lower system through the Zigbee.
The intelligent decision platform image processing comprises the following steps:
s1: the intelligent decision platform is in butt joint with the port terminal camera to acquire a video stream, and the floating garbage appearing on the water surface is identified through a floating garbage identification algorithm and is alarmed and fed back to relevant staff; the floater garbage detection algorithm adopts a deep learning neural network of a Yolov series, a DarkNet_53 network extracts garbage floater characteristics through convolution operation, and a characteristic diagram after 32, 16 and 8 times of sampling is selected to construct a prediction branch for target detection;
s2: the intelligent decision platform calculates the transverse and longitudinal distances between the floating garbage and the orifice by using a graph-on-meter calculation technology according to the snapshot image of the floating garbage, and intelligently determines the relative movement direction and distance of the trash remover; the distance measurement adopts a laser radar, the laser radar is parallel to the optical axis of the camera, the distance is b, and after the laser emitted by the laser radar is calibrated with an image, the center is recorded as P #x l ，y l ) The measured distance is H, and the focal length of the camera is f; according to the imaging principle of the camera, the center coordinate of the obtained image plane is q #0,0) Satisfies the proportional relation of the corresponding sides of the similar triangles,therefore, each pixel corresponds to a length of +.>The target spatial position can be expressed as
S3: the intelligent decision platform takes images according to the floating garbage snapshot, takes the size of the statistical target detection area as the area of the floating garbage by utilizing a graph calculation technology, judges whether the area of the floating garbage exceeds a threshold value according to a preset area threshold value, and alarms under the condition of exceeding the threshold value.
The intelligent driving and controlling system is also provided with a dam orifice water level online intelligent sensing terminal device which is arranged on a vertical wall at one end orifice side of the dam; an on-line intelligent sensing terminal device for the illumination intensity of the environment, which is arranged on a frame of a dam orifice trash cleaning operation area; grab bucket gate hole stations arranged at the starting point and the end point of the operation area of each hole of the dam are arranged on one side of the horizontal travelling track of the trash remover, and the grab bucket gate hole stations are arranged on the online sensing array terminal device; the grab bucket track position online intelligent sensing terminal device is arranged in the grab bucket motion transmission box of the trash remover, and two laser displacement sensors are arranged along the two opposite ends of the travelling track in a collinear manner; the grab bucket lifting height on-line intelligent sensing terminal device is arranged in the grab bucket movement transmission box of the trash remover and used for measuring the lifting height of the trash remover grab bucket moving in the vertical direction; grab bucket working condition load on-line intelligent sensing terminal device which is arranged on slings of grab buckets of the trash remover and used for monitoring the grab bucket working condition load of the trash remover.
The beneficial effects of the invention are as follows:
compared with the prior art, the intelligent control system of the sewage disposal machine based on the vision AI recognition algorithm fully utilizes modern information technology means, combines the current operation and maintenance management mode and the current situation of the control system of the sewage disposal machine of the water inlet trash rack through advanced vision AI technology and computer processing capacity, and establishes a set of intelligent sewage disposal decision and control system based on vision AI. Realize intelligent identification, automatic clear and the long-range semi-automatic operation of decontaminating of collection accuse of trash rack water inlet floater to promote the intelligent level of power station equipment, satisfy the demand of the supervision and the clearance of long-range centralized control center to Liu Ping plug head water inlet trash rack surface of water floating rubbish, alleviate the working strength of main flood season people's work operation simultaneously.
Drawings
FIG. 1 is a schematic diagram of the overall architecture of the system of the present invention;
FIG. 2 is a schematic diagram of a decision platform architecture of the present invention;
FIG. 3 is a schematic diagram of a DarkNet_53 network of the present invention;
FIG. 4 is a flowchart of the garbage float detection algorithm of the present invention;
FIG. 5 is a schematic illustration of the spatial location calculation of the present invention;
fig. 6 is a schematic diagram of the intelligent drive control system of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific embodiments, wherein the exemplary embodiments and descriptions of the invention are for purposes of illustration, but are not intended to be limiting.
The system overall architecture comprises an intelligent decision platform and an intelligent driving control system, wherein the intelligent decision platform is responsible for a system algorithm, performs logic judgment such as trash removal inspection, shape and position recognition, volume measurement and trash removal decision, exceeding an early warning threshold value and the like through a visual AI algorithm, and automatically sends out a trash removal planning command; the intelligent driving control system is used for controlling the trash remover to perform trash removal operation (the existing PLC control system can be utilized as a part of the system), abnormal faults can be automatically judged in the process, the alarm and the shutdown are linked in time, and the trash removal process can be automatically completed or monitored by a remote centralized control personnel in the whole process; meanwhile, the field manual operation function is reserved for exception handling, and the overall architecture principle of the system is shown in figure 1.
The deployment mode is as follows:
cloud computing (private cloud): the identification algorithm can be deployed on a cloud service platform of a centralized control center, is connected with monitoring cameras of the drain grating orifices (Liu Ping gate head trash remover is considered temporarily in one period), and transmits the video recorded in real time to an orifice intelligent trash removal control system and a cloud storage platform which are deployed on the cloud according to a video multicast or unicast protocol through RTSP code streams.
Edge calculation: and identifying by adopting an edge intelligent terminal to perform edge calculation mode. The edge intelligent terminal has edge computing capability, and information such as videos acquired by the information acquisition terminal can be processed in real time through an identification algorithm built in the edge intelligent terminal. The edge computing terminal can be deployed to an orifice industrial control computer to realize the operation of the linkage trash remover.
Cloud edge cooperation: and in a cloud edge cooperative mode, public cloud and private cloud deployment is supported, a micro server or an edge intelligent terminal at the edge part rapidly executes simple scene recognition, customized recognition services of complex scenes and multiple paths of cameras are carried out on the cloud, and video and data are finally transmitted to an orifice intelligent trash removal control system on the cloud server.
According to the current 'less on duty' operation and maintenance management mode and equipment requirements, the cloud computing deployment mode is preferentially considered, namely, the intelligent decision platform is installed in the centralized control center. And accessing monitoring cameras of the drain grating holes (Liu Ping gate head trash remover is considered temporarily in the first period) of each power station, and transmitting the video recorded in real time to an intelligent hole trash removal control system and a cloud storage platform which are deployed on the cloud according to a video multicast or unicast protocol through an RTSP code stream.
The intelligent decision platform takes a perception intelligent technology as a core, and an optical non-contact sensing device (camera) is used for automatically receiving a large amount of water scene image processing and performing intelligent analysis so as to obtain an information control machine or flow. And the intelligent analysis decision platform is built by fully utilizing technologies such as the Internet, the 5G, the Internet of things and the like, so that the early warning, the processing and the tracking of the water surface pollution are realized, and the architecture principle is shown in figure 2.
(1) Float rubbish detection snapshot: the monitoring equipment is distributed through the orifice to acquire video stream data, so that real-time detection snapshot of the floating garbage on the water surface is realized, the intelligent body actively recognizes, and the snapshot is kept.
(2) And (3) on-drawing calculation detection: the calculation of the position of the floating garbage detected and identified and the calculation of the area of the floating garbage are realized by using the on-map calculation technology, and the relative movement direction and distance of the trash remover are calculated in an auxiliary mode.
(3) Alarming for abnormal conditions: and the function of timely alarming is realized for identifying abnormal conditions such as floating garbage and floating garbage area exceeding a threshold value.
The intelligent driving control system is in communication connection with the orifice intelligent cleaning control system through an Ethernet, is in communication connection with the cleaning site centralized control system (industrial control computer) through the Ethernet, is in communication connection with the cleaning site centralized control system (industrial control computer) through Zigbee, and is in communication connection with the environment sensing lower system (embedded microcontroller) through Zigbee (Zigbee). The layout scheme is shown in fig. 3;
the intelligent decision platform construction is mainly divided into an image algorithm module, an abnormal condition alarm module and an algorithm configuration module. Firstly, identifying floating garbage on the water surface through an image algorithm, alarming to relevant staff, confirming the position and the area of the floating garbage through calculation on a map, providing guidance for cleaning of the cleaner, and supporting manual adjustment algorithm configuration by a platform.
(1) Image algorithm module
a float garbage identification algorithm
The platform is abutted against the terminal camera of the orifice, a video stream is obtained, floating garbage appearing on the water surface is identified through a floating garbage identification algorithm, and an alarm is given and fed back to relevant staff.
The floater garbage detection algorithm adopts a Yolov series deep learning neural network, wherein a DarkNet_53 is shown in fig. 3, the DarkNet_53 network extracts garbage floater characteristics through convolution operation, and a characteristic diagram after 32, 16 and 8 times sampling is selected to construct a prediction branch for target detection. The system framework of the whole algorithm is shown in fig. 4;
1. combining Liu Ping brake application scenes to collect basic data and functional requirements;
2. according to the data information and the function requirements, developing vision AI recognition software, respectively verifying from two algorithms of scum type recognition and scum area recognition, and determining an optimal prototype algorithm by training for 3-6 months and taking precision and efficiency as indexes as data support of final research and development application of the system.
The floater garbage detection algorithm adopts a Yolov series deep learning neural network, wherein a DarkNet_53 is shown in fig. 3, the DarkNet_53 network extracts garbage floater characteristics through convolution operation, and a characteristic diagram after 32, 16 and 8 times sampling is selected to construct a prediction branch for target detection. The system framework of the whole algorithm is shown in fig. 4;
in the algorithm, k-means are mainly used for carrying out cluster analysis on a data set to generate a priori frame, the priori frame is used in 3 prediction branches, CAM networks are respectively added in the 3 prediction branches for further extracting target position points, after network training is finished, the weight of a target pixel point corresponding to a positioning frame in each Scale is extracted, the weight is added into a weight model for detecting the water surface floaters, and therefore the coordinate information of the positioning frame is replaced by the pixel point through the weight model by a water surface floaters test set during detection and is drawn on an image, and the positioning of the target on the image is realized.
b, calculating the position of floating garbage
The platform calculates the transverse and longitudinal distances between the floating garbage and the orifice by using a graph-on-meter calculation technology according to the snapshot image of the floating garbage, and intelligently determines the relative movement direction and distance of the trash remover.
In the technical module, a laser radar is adopted for distance measurement, the module is parallel to the optical axis of a camera, the distance is b, and after laser emitted by the laser radar module is calibrated with an image, the center is recorded as P # l x，y l ) The measured distance is H and the camera focal length is f. According to the imaging principle of the camera, as shown in figure 5, the center coordinate of the obtained image plane is q #0,0) Satisfies the proportional relation of the corresponding sides of the similar triangles,therefore, each pixel corresponds to a length of +.>The target spatial position can be expressed as
c, calculating the area of floating garbage
The platform takes images according to the floating garbage, takes the size of the statistical target detection area as the area of the floating garbage by using a graph-on-graph calculation technology, judges whether the area of the floating garbage exceeds a threshold value according to a preset area threshold value, and alarms the condition of the exceeding threshold value.
Meanwhile, the platform automatically calculates the cleaning times of the trash remover and the actual positions of multiple cleaning for the situation that the area exceeds the threshold value, so that the cleaning comprehensiveness of the trash remover is ensured.
(2) Abnormal condition alarm module
The platform intelligently recognizes the abnormal condition of the water surface and pushes the abnormal condition to relevant staff in a popup window or short message mode, and reminds the staff to confirm the treatment.
Supporting manual setting and modification of alarm thresholds
(3) Algorithm configuration module
a identification frequency configuration
The system can configure the algorithm identification frequency according to the actual demands, adjust the floating garbage identification interval and adjust the configuration according to the most efficient mode.
b remote centralized configuration calculation force
The system can remotely and intensively configure calculation force on the platform according to actual requirements (field test).
The intelligent driving control system (industrial control computer) is arranged in the 400V room industrial television cabinet and is in communication connection with the intelligent decontamination control system of the orifice through the Ethernet.
The track driving lower system (PLC-1, former Siemens 200 PLC) is arranged in the control cabinet of the original trash remover and is in communication connection with the trash removal site centralized control system (industrial control computer) through the Ethernet.
The grab bucket driving and controlling lower system (PLC-2, newly added PLC system) is arranged in the grab bucket motion transmission box of the original trash remover and is in communication connection with the trash cleaning site centralized control system (industrial control computer) through Zigbee (Zigbee).
The environment sensing lower system (embedded microcontroller) is arranged at an environment sensing point and is in communication connection with the pollution cleaning site centralized control system (industrial control computer) through Zigbee.
The layout scheme is shown in fig. 6; the intelligent driving control system is in communication connection with the orifice intelligent cleaning control system through an Ethernet, is in communication connection with the cleaning site centralized control system (industrial control computer) through the Ethernet, is in communication connection with the cleaning site centralized control system (industrial control computer) through Zigbee, and is in communication connection with the environment sensing lower system (embedded microcontroller) through Zigbee (Zigbee).
Dam orifice water level sensing:
the dam orifice water level on-line intelligent sensing terminal device is arranged on a vertical wall at one end orifice side of the dam, is convenient for installation and detection of a drop-in water level sensor, and is in host question-answer communication connection with a sewage disposal site centralized control system (industrial control computer) through Zigbee.
Ambient light intensity sensing:
the on-line intelligent sensing terminal device for the ambient light intensity is arranged on the border of the dam orifice trash cleaning operation area, is convenient for the installation and detection of the light intensity sensor, and is in host question-answer communication connection with a trash cleaning site centralized control system (industrial control computer) through Zigbee.
Grab bucket gate station sensing:
the grab bucket gate hole station on-line sensing array terminal device is arranged on one side of a horizontal travelling track of the trash remover and is positioned at a starting point and an ending point of an operation area of each hole opening of the dam, so that the grab bucket of the trash remover and the grab bucket can be conveniently sensed in the hole position area, and the grab bucket gate hole station is in signal connection with a track driving and controlling lower system (PLC-1) through DIO.
Grab rail position sensing:
the grab bucket track position on-line intelligent sensing terminal device is arranged in a grab bucket motion transmission box of the trash remover, and the two laser displacement sensors are arranged along the two opposite ends of the travelling track in a collinear manner, so that the trash remover grab bucket motion transmission box and the grab bucket can be conveniently measured in horizontal position, and the grab bucket motion transmission box are in communication connection with a grab bucket driving control lower system (PLC-2) through serial ports.
Grab bucket elevation sensing:
the grab bucket lifting height on-line intelligent sensing terminal device is arranged in a grab bucket movement transmission box of the trash remover, the lifting height of the trash remover grab bucket moving in the vertical direction is measured, and the grab bucket lifting height is in question-answer communication connection with a grab bucket driving lower system (PLC-2) through RS 485.
Grab bucket operating mode load sensing:
the grab bucket working condition load on-line intelligent sensing terminal device is arranged on a sling of the grab bucket of the trash remover, monitors the grab bucket working condition load of the trash remover, and is in question-answer communication connection with a grab bucket driving and controlling lower system (PLC-2) through RS 485.
The technical scheme of the invention is not limited to the specific embodiment, and all technical modifications made according to the technical scheme of the invention fall within the protection scope of the invention.
Claims (5)
1. A trash remover intelligent control system based on a visual AI recognition algorithm is characterized in that: the intelligent decision platform carries out the logic judgment of the dirt cleaning inspection, the shape and position recognition, the accumulation measurement, the dirt cleaning decision and the exceeding of the early warning threshold through the vision AI algorithm, and automatically sends a dirt cleaning plan command to the intelligent drive control system, and the intelligent drive control system receives the control command of the intelligent decision platform to control the dirt cleaner to carry out the dirt cleaning operation.
2. The intelligent control system of the trash remover based on the visual AI recognition algorithm as set forth in claim 1, wherein: the intelligent decision platform takes a perception intelligent technology as a core, and an optical non-contact sensing device is used for automatically receiving a large amount of water scene images for processing and performing intelligent analysis so as to obtain an information control machine or flow, and the internet, 5G or the Internet of things is fully utilized to build the intelligent analysis decision platform for early warning, processing and tracking of water surface pollution.
3. The intelligent control system of the trash remover based on the visual AI recognition algorithm as set forth in claim 1, wherein: the intelligent driving control system is in communication connection with the orifice intelligent cleaning control system through an Ethernet, is in communication connection with the cleaning site centralized control system through the Ethernet, is in communication connection with the cleaning site centralized control system through Zigbee, and is in communication connection with the environment sensing lower system through the Zigbee.
4. The intelligent control system of the trash remover based on the visual AI recognition algorithm as set forth in claim 2, wherein: the intelligent decision platform image processing comprises the following steps:
s1: the intelligent decision platform is in butt joint with the port terminal camera to acquire a video stream, and the floating garbage appearing on the water surface is identified through a floating garbage identification algorithm and is alarmed and fed back to relevant staff; the floater garbage detection algorithm adopts a deep learning neural network of a Yolov series, a DarkNet_53 network extracts garbage floater characteristics through convolution operation, and a characteristic diagram after 32, 16 and 8 times of sampling is selected to construct a prediction branch for target detection;
s2: the intelligent decision platform calculates the transverse and longitudinal distances between the floating garbage and the orifice by using a graph-on-meter calculation technology according to the snapshot image of the floating garbage, and intelligently determines the relative movement direction and distance of the trash remover; the distance measurement adopts a laser radar, the laser radar is parallel to the optical axis of the camera, the distance is b, and after the laser emitted by the laser radar is calibrated with an image, the center is recorded as P #x l ， y l ) The measured distance is H, and the focal length of the camera is f; according to the imaging principle of the camera, the center coordinate of the obtained image plane is q #0,0) Satisfies the proportional relation of the corresponding sides of the similar triangles,therefore, each pixel corresponds to a length of +.>The target spatial position can be expressed as
S3: the intelligent decision platform takes images according to the floating garbage snapshot, takes the size of the statistical target detection area as the area of the floating garbage by utilizing a graph calculation technology, judges whether the area of the floating garbage exceeds a threshold value according to a preset area threshold value, and alarms under the condition of exceeding the threshold value.
5. The intelligent control system of a trash remover based on visual AI recognition algorithm of claim 3, wherein: the intelligent driving and controlling system is also provided with a dam orifice water level online intelligent sensing terminal device which is arranged on a vertical wall at one end orifice side of the dam; an on-line intelligent sensing terminal device for the illumination intensity of the environment, which is arranged on a frame of a dam orifice trash cleaning operation area; grab bucket gate hole stations arranged at the starting point and the end point of the operation area of each hole of the dam are arranged on one side of the horizontal travelling track of the trash remover, and the grab bucket gate hole stations are arranged on the online sensing array terminal device; the grab bucket track position online intelligent sensing terminal device is arranged in the grab bucket motion transmission box of the trash remover, and two laser displacement sensors are arranged along the two opposite ends of the travelling track in a collinear manner; the grab bucket lifting height on-line intelligent sensing terminal device is arranged in the grab bucket movement transmission box of the trash remover and used for measuring the lifting height of the trash remover grab bucket moving in the vertical direction; grab bucket working condition load on-line intelligent sensing terminal device which is arranged on slings of grab buckets of the trash remover and used for monitoring the grab bucket working condition load of the trash remover.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310632391.8A CN116665102A (en) | 2023-05-31 | 2023-05-31 | Intelligent control system of trash remover based on vision AI recognition algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310632391.8A CN116665102A (en) | 2023-05-31 | 2023-05-31 | Intelligent control system of trash remover based on vision AI recognition algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116665102A true CN116665102A (en) | 2023-08-29 |
Family
ID=87723727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310632391.8A Pending CN116665102A (en) | 2023-05-31 | 2023-05-31 | Intelligent control system of trash remover based on vision AI recognition algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665102A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117702835A (en) * | 2023-11-14 | 2024-03-15 | 曲阜恒威水工机械有限公司 | Intelligent grabbing arm trash remover and trash removal control system |
-
2023
- 2023-05-31 CN CN202310632391.8A patent/CN116665102A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117702835A (en) * | 2023-11-14 | 2024-03-15 | 曲阜恒威水工机械有限公司 | Intelligent grabbing arm trash remover and trash removal control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114373245B (en) | Intelligent inspection system based on digital power plant | |
| CN110533885B (en) | Urban waterlogging monitoring and early warning system and method | |
| CN105835063A (en) | Indoor inspection robot system for substation and inspection method for indoor inspection robot system | |
| CN210377085U (en) | Underground water pump house inspection system for coal mine | |
| CN109348179B (en) | Road monitoring and detecting system and method based on artificial intelligence | |
| CN205685341U (en) | A kind of combined track formula transformer station indoor crusing robot system | |
| CN116665102A (en) | Intelligent control system of trash remover based on vision AI recognition algorithm | |
| CN104047248A (en) | Combined type rail pavement automatic cleaning vehicle system | |
| CN113487048A (en) | Drainage tunnel operation safety monitoring and maintenance system and method | |
| CN210865032U (en) | Urban waterlogging monitoring and early warning system | |
| CN113798244A (en) | Water spraying effect detection device, transformer substation water washing robot and method | |
| CN111912857A (en) | Diversion tunnel rope climbing detection robot and detection method thereof | |
| CN109339209B (en) | Intelligent sewer well lid system capable of being connected with network and control method thereof | |
| CN116610061B (en) | Digital management and control system for whole river channel garbage cleaning process | |
| CN109146338A (en) | A kind of power station Production Scheduling System and method | |
| CN113239747A (en) | Intelligent blowdown system of removing obstacles on water based on computer vision | |
| CN116743069A (en) | Cleaning control method of photovoltaic module, cleaning robot and photovoltaic cleaning system | |
| CN117689360A (en) | Manufacturing method of intelligent inspection integrated platform of fan | |
| CN111416964A (en) | Remote image intelligent identification method for hydraulic engineering deformation | |
| CN209784768U (en) | Ship line-crossing detection system based on laser detection technology | |
| CN110009762A (en) | One kind being exclusively used in sewage treatment plant's biological reaction pool intelligent inspection system | |
| CN114637245A (en) | Road surface dust fall control system | |
| CN112184078B (en) | Automatic inspection system for closed water treatment facility | |
| CN113660334A (en) | River course floater monitoring and early warning dispatch system based on big data | |
| CN118713308B (en) | Intelligent inspection method and inspection robot based on photovoltaic power station |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |